Model: GELU Model: 4 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 33 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.5560. Min Range: -3.5560

Max Act: 3.5246. Min Act: -0.1700

Data Index: 1065012 (C4 (Web Text))

Max Activating Token Index: 323

Text #1

Max Range: 3.5560. Min Range: -3.5560

Max Act: 3.5560. Min Act: -0.1700

Data Index: 647461 (C4 (Web Text))

Max Activating Token Index: 558

Text #2

Max Range: 3.5560. Min Range: -3.5560

Max Act: 3.4933. Min Act: -0.1700

Data Index: 210386 (C4 (Web Text))

Max Activating Token Index: 254

Text #3

Max Range: 3.5560. Min Range: -3.5560

Max Act: 3.4306. Min Act: -0.1700

Data Index: 1286872 (C4 (Web Text))

Max Activating Token Index: 890

Text #4

Max Range: 3.5560. Min Range: -3.5560

Max Act: 3.4306. Min Act: -0.1700

Data Index: 679327 (C4 (Web Text))

Max Activating Token Index: 716

Text #5

Max Range: 3.5560. Min Range: -3.5560

Max Act: 3.4306. Min Act: -0.1700

Data Index: 363744 (C4 (Web Text))

Max Activating Token Index: 97

Text #6

Max Range: 3.5560. Min Range: -3.5560

Max Act: 3.3992. Min Act: -0.1700

Data Index: 732129 (C4 (Web Text))

Max Activating Token Index: 731

Text #7

Max Range: 3.5560. Min Range: -3.5560

Max Act: 3.3992. Min Act: -0.1700

Data Index: 1087352 (C4 (Web Text))

Max Activating Token Index: 79

Text #8

Max Range: 3.5560. Min Range: -3.5560

Max Act: 3.3992. Min Act: -0.1700

Data Index: 502448 (C4 (Web Text))

Max Activating Token Index: 890

Text #9

Max Range: 3.5560. Min Range: -3.5560

Max Act: 3.3679. Min Act: -0.1700

Data Index: 881132 (C4 (Web Text))

Max Activating Token Index: 620

Text #10

Max Range: 3.5560. Min Range: -3.5560

Max Act: 3.3365. Min Act: -0.1700

Data Index: 264077 (C4 (Web Text))

Max Activating Token Index: 194

Text #11

Max Range: 3.5560. Min Range: -3.5560

Max Act: 3.3679. Min Act: -0.1700

Data Index: 764759 (C4 (Web Text))

Max Activating Token Index: 299

Text #12

Max Range: 3.5560. Min Range: -3.5560

Max Act: 3.3679. Min Act: -0.1700

Data Index: 1121434 (C4 (Web Text))

Max Activating Token Index: 972

Text #13

Max Range: 3.5560. Min Range: -3.5560

Max Act: 3.3679. Min Act: -0.1700

Data Index: 230247 (C4 (Web Text))

Max Activating Token Index: 894

Text #14

Max Range: 3.5560. Min Range: -3.5560

Max Act: 3.3679. Min Act: -0.1700

Data Index: 1117346 (C4 (Web Text))

Max Activating Token Index: 631

Text #15

Max Range: 3.5560. Min Range: -3.5560

Max Act: 3.3679. Min Act: -0.1700

Data Index: 268822 (C4 (Web Text))

Max Activating Token Index: 654

Text #16

Max Range: 3.5560. Min Range: -3.5560

Max Act: 3.3679. Min Act: -0.1700

Data Index: 907094 (C4 (Web Text))

Max Activating Token Index: 998

Text #17

Max Range: 3.5560. Min Range: -3.5560

Max Act: 3.3365. Min Act: -0.1700

Data Index: 1071364 (C4 (Web Text))

Max Activating Token Index: 808

Text #18

Max Range: 3.5560. Min Range: -3.5560

Max Act: 3.3365. Min Act: -0.1700

Data Index: 760563 (C4 (Web Text))

Max Activating Token Index: 106

Text #19

Max Range: 3.5560. Min Range: -3.5560

Max Act: 3.3365. Min Act: -0.1700

Data Index: 357142 (C4 (Web Text))

Max Activating Token Index: 599